roberta-base-thai-spm-ud-goeswith / tokenizer_config.json
KoichiYasuoka's picture
initial release
5b12b0e
raw
history blame contribute delete
459 Bytes
{
"bos_token": "[CLS]",
"cls_token": "[CLS]",
"do_lower_case": false,
"eos_token": "[SEP]",
"keep_accents": true,
"mask_token": {
"__type": "AddedToken",
"content": "[MASK]",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"pad_token": "[PAD]",
"remove_space": true,
"sep_token": "[SEP]",
"tokenizer_class": "RemBertTokenizerFast",
"unk_token": "[UNK]"
}